02.06.2026
Benjamin Lange: The Real Risk of AI Agents Is Manipulation Through Kindness
Research Film
As AI moves from answering questions to managing our lives, how do we make sure we stay in control?
«As we delegate more to AI agents, we risk undermining our autonomy.»
Benjamin Lange
MCML Junior Research Group Leader
MCML Junior Research Group Leader Benjamin Lange examines how trust in AI agents can itself become a source of risk. His research focuses on how to govern these systems responsibly, with particular attention to those most vulnerable to their influence.
In this video series, discover how MCML researchers are bridging theory and practice to build AI systems that prioritize accessibility, sovereignty, and impact.
©MCML
The film was produced and edited by Nicole Huminski and Nikolai Huber.
Related
15.10.2026
When Flatter Is Not Always Better
In their ICML 2026 paper, MCML researchers show why the flattest regions found during neural network training are not always the best.
14.10.2026
MCML at the LRZ Open Day 2026
MCML PI Benjamin Lange contributed to the program of the LRZ Open Day in Garching on October 3, 2026.
